From 43be8fef76a7f8d718443af23019714aa612d40e Mon Sep 17 00:00:00 2001 From: acosta123 <42226556+acosta123@users.noreply.github.com> Date: Mon, 3 Jun 2019 10:37:10 +0800 Subject: [PATCH] Update doc/fluid/advanced_usage/paddle_slim/paddle_slim_en.md Co-Authored-By: Hao Wang <31058429+haowang101779990@users.noreply.github.com> --- doc/fluid/advanced_usage/paddle_slim/paddle_slim_en.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/fluid/advanced_usage/paddle_slim/paddle_slim_en.md b/doc/fluid/advanced_usage/paddle_slim/paddle_slim_en.md index 8164019ed..4600bad90 100644 --- a/doc/fluid/advanced_usage/paddle_slim/paddle_slim_en.md +++ b/doc/fluid/advanced_usage/paddle_slim/paddle_slim_en.md @@ -37,7 +37,7 @@ Paddle-Slim tool library has the following features: Refer to [demos](https://github.com/PaddlePaddle/models/blob/develop/PaddleSlim/docs/demo.md) for more details -### Good Performance +### Optimized Effects - For MobileNetV1 model with less redundant information, the convolution core pruning strategy can still reduce the size of the model and maintain as little accuracy loss as possible. - The distillation strategy can increase the accuracy of the origin model dramatically. -- GitLab